Opus 5.5 手写 169 行 JS 神经网络可视化螺旋分类
从零实现前向、反向传播和 Adam，在双螺旋数据上把未见测试点准确率从 24.5% 训到 99.2%，并渲染成 1080p 动画。
This network had never seen a single test point and still got 99.2% of them right. Before training it scored 24.5%, below the 33% you'd get by picking colours at random. The task is the classic three-arm spiral. 600 training points, 3 colours, and you can't separate them with straight lines. The network has 2 inputs, two hidden layers of 32 neurons and 1,251 weights. Epoch 0: 24.5% on unseen points Epoch 100: 98.7% Epoch 150: crosses 99% Epoch 1,500: 99.2% test, 99.7% train The left side is the network's guess for every spot on the plane. The 16 tiles on the right show what individual hidden neurons react to. Each one draws a simple wavy cut. The output layer combines them into the spiral. Claude Opus 5.5 wrote the whole thing from scratch in Claude Code: forward pass, backprop and the Adam optimizer in 169 lines of JavaScript, no ML library. Training takes 10 seconds, the 1080p render about 2.5 minutes.
这条是引用着另一条写的：「Opus 5.5 用 105 行 JS 生成万鸟群飞视频」